Drug Recommendations Using a “Reviews and Sentiment Analysis” by a Recurrent Neural Network
Sk. Gousiya Begum, P. Kiran Sree
Abstract
Drug Recommendation systems have the capability to recommend drugs. On daily basis, a huge amount of data is being generated by the patients. All the valuable data can be properly utilized for creating a reliable drug recommendation system. In this paper, the researchers aimed to propose a system for drug recommendations. The main scope of the system is to predict the correct medication based on reviews and ratings. The proposed system uses Natural Language Processing techniques (NLP) and Recurrent Neural Network (RNN). The researchers also considered various metrices such as precision, recall, accuracy, f1 Score, roc curve as the measures of the system performance. Natural Language Processing techniques were used for gathering useful information from patients data, and RNN is a machine learning methodology, that works really well when it comes to analysing textual data. The system considers various patient data attributes like age, gender, dosage, medical history, symptom in order to make appropriate predictions. As the result, the proposed system has the potential to help medical professionals in making informed drug recommendations.